Text2Motion: From Natural Language Instructions to Feasible Plans

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Kevin, Agia, Christopher, Migimatsu, Toki, Pavone, Marco, Bohg, Jeannette
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916462444150784
author Lin, Kevin
Agia, Christopher
Migimatsu, Toki
Pavone, Marco
Bohg, Jeannette
author_facet Lin, Kevin
Agia, Christopher
Migimatsu, Toki
Pavone, Marco
Bohg, Jeannette
contents We propose Text2Motion, a language-based planning framework enabling robots to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural language instruction, our framework constructs both a task- and motion-level plan that is verified to reach inferred symbolic goals. Text2Motion uses feasibility heuristics encoded in Q-functions of a library of skills to guide task planning with Large Language Models. Whereas previous language-based planners only consider the feasibility of individual skills, Text2Motion actively resolves geometric dependencies spanning skill sequences by performing geometric feasibility planning during its search. We evaluate our method on a suite of problems that require long-horizon reasoning, interpretation of abstract goals, and handling of partial affordance perception. Our experiments show that Text2Motion can solve these challenging problems with a success rate of 82%, while prior state-of-the-art language-based planning methods only achieve 13%. Text2Motion thus provides promising generalization characteristics to semantically diverse sequential manipulation tasks with geometric dependencies between skills.
format Preprint
id arxiv_https___arxiv_org_abs_2303_12153
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Text2Motion: From Natural Language Instructions to Feasible Plans
Lin, Kevin
Agia, Christopher
Migimatsu, Toki
Pavone, Marco
Bohg, Jeannette
Robotics
Artificial Intelligence
Machine Learning
We propose Text2Motion, a language-based planning framework enabling robots to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural language instruction, our framework constructs both a task- and motion-level plan that is verified to reach inferred symbolic goals. Text2Motion uses feasibility heuristics encoded in Q-functions of a library of skills to guide task planning with Large Language Models. Whereas previous language-based planners only consider the feasibility of individual skills, Text2Motion actively resolves geometric dependencies spanning skill sequences by performing geometric feasibility planning during its search. We evaluate our method on a suite of problems that require long-horizon reasoning, interpretation of abstract goals, and handling of partial affordance perception. Our experiments show that Text2Motion can solve these challenging problems with a success rate of 82%, while prior state-of-the-art language-based planning methods only achieve 13%. Text2Motion thus provides promising generalization characteristics to semantically diverse sequential manipulation tasks with geometric dependencies between skills.
title Text2Motion: From Natural Language Instructions to Feasible Plans
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2303.12153